Mathematical Origins of Machine Learning | Teaching Computers to Learn, Part 2

Поделиться
HTML-код
  • Опубликовано: 2 ноя 2024

Комментарии • 48

  • @sandrinjoy
    @sandrinjoy 2 месяца назад +46

    This has to be the best Intro to "Calculus in ML" explanation video ever. Hats off!!!

  • @avi12
    @avi12 2 месяца назад +17

    This video MUST have 10s of millions of views

  • @AbdullahCumhur
    @AbdullahCumhur 2 месяца назад +7

    I always saw this "Least Squares" method on "How to make AI" videos but I never could understand why did we do that. But this video makes it VERY clear :) I feel like I can make chat gpt in 1 day now lol

  • @nicholasziglio
    @nicholasziglio Месяц назад +1

    Hands down the best explanation of the chain rule I've ever seen!

  • @genericpenguin
    @genericpenguin 2 месяца назад +2

    How does this channel not have more subs? Every video is an object lesson in clarity.

  • @liamwoodleigh
    @liamwoodleigh 2 месяца назад +8

    Amazing video. Really enjoyed and learned a lot. Thanks!

  • @NachitenRemix
    @NachitenRemix 2 месяца назад +1

    You have an excellent ability to teach this very complex topics in an entertaining fashion. The animations also make it very easy to follow. Thank you for all your work. ❤❤

  • @Chrisionvision
    @Chrisionvision 2 месяца назад +1

    I love this series so far!

  • @softwaresirppi
    @softwaresirppi 2 месяца назад +2

    that was awesome! looking forward to part 3!

  • @harshvardhanagrawal516
    @harshvardhanagrawal516 20 дней назад

    Wow If I take your math class, I could join MIT, Stanford or Oxford! high Quality stuff!

  • @nedko
    @nedko 2 месяца назад +1

    OMG. It's so clear now. Thank you!

  • @n8wrl
    @n8wrl 2 месяца назад +1

    This is really well done. Thank you!

  • @AJ-ju7tl
    @AJ-ju7tl 2 месяца назад +1

    awesome summary! keep it up!

  • @msameen99
    @msameen99 2 месяца назад +1

    Thanks a lot, keep the GREAT work

  • @Endou47
    @Endou47 2 месяца назад +1

    I love your videos, Brian.

  • @MadlipzMarathi
    @MadlipzMarathi 2 месяца назад

    small correction, gradients tell which way function increase, we take negative of gradients to decent
    (but not always eg rl where you want to maximize reward)

  • @adamjones471
    @adamjones471 2 месяца назад +2

    this was beautiful

  • @dm82936
    @dm82936 2 месяца назад +1

    fantastic

  • @aincrad6383
    @aincrad6383 2 месяца назад +1

    beautiful. THank you brian

  • @ashe_
    @ashe_ 2 месяца назад +1

    This has unlocked AI for me. Thanks!

  • @vinniepeterss
    @vinniepeterss 2 месяца назад +3

    maybe the obstacle in artificial intelligence to be able to think like human is the capability to memorize and think at the same time? like for us, our memory can be like a "time machine" that we can go back to, and with our capability to rationalize, imaginate and think foward makes us "smart". something that a robot with zeros and ones can't

    • @drdca8263
      @drdca8263 2 месяца назад +1

      Hm? Being based on 1s & 0s doesn’t prevent retrieving records of previous inputs and processing.
      And, whatever processing can be done, can be done in relation to those retrieved records.

    • @vinniepeterss
      @vinniepeterss 2 месяца назад

      ​@drdca8263 oh, really? i didn't know that. i'm just speculating...

    • @drdca8263
      @drdca8263 2 месяца назад +1

      @@vinniepeterss Well, you can have e.g. a video feed, and a program can do processing on recorded video, right? (Doesn’t have to be video, just an example)
      Maybe I’ve misunderstood what you meant. Did you maybe mean something like, being able to efficiently find the records of past events that are relevant to what is currently going on?
      I think that task is probably one which people might be significantly better at than computers, and maybe in a way that results from how the computer hardware works? Idk.
      That seems at least sorta similar to what you were suggesting?

    • @vinniepeterss
      @vinniepeterss 2 месяца назад +2

      ​​@@drdca8263 well, the way i look at it is, that computer cannot "think" back and foward like the way we humans do it i guess? ok. for example if i need you to answer some idea that never been tested before and we want to test it, the way we do it is to remembering what we learn with respect to the idea itself (memorizing, but sorta looking back) and combine with speculative results (imaginatively). that's what the computer cannot do maybe?
      i dunno man, i come from third world country. maybe when i wrote that comments i'm full of thoughts but now i'm lost jajajaja

  • @yiannchrst
    @yiannchrst 2 месяца назад

    When you described how gradient descent works the first thing I thought was "what about local minima?".
    Anyway, thanks for the video!

  • @esmondadjei
    @esmondadjei 2 месяца назад

    great video.

  • @CosmosDev-q4s
    @CosmosDev-q4s 2 месяца назад

    Can you cover modules?

  • @vinniepeterss
    @vinniepeterss 2 месяца назад +3

    ❤❤

  • @eversonmay
    @eversonmay 7 дней назад

    nice

  • @kingki1953
    @kingki1953 2 месяца назад +6

    Let the machine cooks 🗣️🔥🔥

  • @rockethm512
    @rockethm512 16 дней назад

    Where's the third part 😭

  • @newlife-9316
    @newlife-9316 2 месяца назад

    Backpropagation?

  • @i_like_commenting_ok
    @i_like_commenting_ok 2 месяца назад +1

    ok

  • @stillprophet7529
    @stillprophet7529 2 месяца назад

    Holy shit es war echt wii sports, ich habs gedacht aber dachte das kann eigentlich nicht :D

  • @cw6043
    @cw6043 2 месяца назад

    tbh I'm not interested in ML. I hope you get back to less scab/scam based nicer algorithms.

    • @KushLemon
      @KushLemon Месяц назад

      Not everything that you don't understand is a "scam".

  • @Ozay1998
    @Ozay1998 2 месяца назад

    Thats just statistics thats it. Idk why implementing this on a computer gives it another name

    • @someindianguy4471
      @someindianguy4471 2 месяца назад

      Numerical math*

    • @theresalwaysanotherway3996
      @theresalwaysanotherway3996 2 месяца назад +2

      because doing it for say, 20 data points vs 20 million data points requires a large amount of extra knowledge, and starts introducing engineering problems, not just mathematical ones.

    • @ooogabooga5111
      @ooogabooga5111 2 месяца назад +4

      you can say everything is mathamatics in that way, why have names for anything.

    • @Ozay1998
      @Ozay1998 2 месяца назад

      @@ooogabooga5111 wdym, they already have names. im talking about renaming

    • @thezipcreator
      @thezipcreator 2 месяца назад +2

      mathematics is the art of giving different names to the same things

  • @KushLemon
    @KushLemon Месяц назад

    Next video when?